42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1410
- Accuracy: 0.9662
- Dt Accuracy: 0.9662
- Df Accuracy: 0.9645
- Unlearn Overall Accuracy: 0.2386
- Unlearn Time: None
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.1441 | 0.977 | 0.2189 | 0.2189 | None |
| 0.5375 | 2.0 | 782 | 0.1401 | 0.9735 | 0.2245 | 0.2245 | None |
| 0.4885 | 3.0 | 1173 | 0.1384 | 0.9805 | 0.2135 | 0.2135 | None |
| 0.4737 | 4.0 | 1564 | 0.1457 | 0.9715 | 0.2277 | 0.2277 | None |
| 0.4737 | 5.0 | 1955 | 0.1383 | 0.9715 | 0.2276 | 0.2276 | None |
| 0.4511 | 6.0 | 2346 | 0.1378 | 0.971 | 0.2285 | 0.2285 | None |
| 0.4362 | 7.0 | 2737 | 0.1382 | 0.9675 | 0.2339 | 0.2339 | None |
| 0.4182 | 8.0 | 3128 | 0.1463 | 0.963 | 0.2409 | 0.2409 | None |
| 0.4118 | 9.0 | 3519 | 0.1383 | 0.9695 | 0.2308 | 0.2308 | None |
| 0.4118 | 10.0 | 3910 | 0.1410 | 0.9645 | 0.2386 | 0.2386 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0